Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Albums and music

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estudio
    -0.07
     Huge
    -0.06
     contin
    -0.06
     nova
    -0.06
     quitting
    -0.06
     proporcion
    -0.06
     wurden
    -0.06
    -option
    -0.06
     loving
    -0.06
    .one
    -0.06
    POSITIVE LOGITS
     russian
    0.07
    /store
    0.07
    [edge
    0.07
     speaking
    0.06
    顶
    0.06
    "],["
    0.06
    .ir
    0.06
    Speaking
    0.06
     ฿
    0.06
    .CreateInstance
    0.06
    Act Density 0.053%

    No Known Activations